© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169614
    Prev
    Next
    INDEX
    Explanations

    code or commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sample
    0.49
    いま
    0.41
     Sample
    0.39
    শরণ
    0.37
    喚
    0.36
    급
    0.36
    She
    0.36
    Gün
    0.36
     sample
    0.35
    cie
    0.35
    POSITIVE LOGITS
     |,
    0.38
     ಐ
    0.37
    ',
    0.36
    FORD
    0.35
    ",
    0.35
    шем
    0.34
    \",
    0.34
     المرا
    0.34
     actomyosin
    0.34
     অ্যাক
    0.33
    Activations Density 0.006%

    No Known Activations